Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    bottom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .／
    -0.07
    .ef
    -0.07
    istros
    -0.06
    AtPath
    -0.06
    セ
    -0.06
    annes
    -0.06
     пат
    -0.06
    -divider
    -0.06
     Superior
    -0.06
     nejd
    -0.06
    POSITIVE LOGITS
    -info
    0.07
     proceeds
    0.07
     по
    0.06
    charge
    0.06
    TPL
    0.06
     perfil
    0.06
     oxygen
    0.06
    oub
    0.06
     joins
    0.06
     Bind
    0.06
    Act Density 0.087%

    No Known Activations